<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>JADT | Stefano Blando</title><link>https://stefano-blando.github.io/en/tags/jadt/</link><atom:link href="https://stefano-blando.github.io/en/tags/jadt/index.xml" rel="self" type="application/rss+xml"/><description>JADT</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-US</language><lastBuildDate>Thu, 16 Jul 2026 00:00:00 +0000</lastBuildDate><image><url>https://stefano-blando.github.io/media/icon_hu_8d0dee6c10a3c598.png</url><title>JADT</title><link>https://stefano-blando.github.io/en/tags/jadt/</link></image><item><title>VADISTAT Award for Best Scientific Contribution at JADT 2026</title><link>https://stefano-blando.github.io/en/blog/vadistat-award-2026/</link><pubDate>Thu, 16 Jul 2026 00:00:00 +0000</pubDate><guid>https://stefano-blando.github.io/en/blog/vadistat-award-2026/</guid><description>&lt;p&gt;I received the &lt;strong&gt;&amp;ldquo;2026 Associazione VADISTAT - Per Simona Balbi&amp;rdquo;&lt;/strong&gt; award during the &lt;strong&gt;18th International Conference JADT 2026&lt;/strong&gt; (&lt;em&gt;Journées internationales d&amp;rsquo;Analyse statistique des Données Textuelles&lt;/em&gt;) held in Palermo.&lt;/p&gt;
&lt;p&gt;The prize, awarded for the best scientific contribution presented by researchers under 35 in statistical textual data analysis, recognized the paper &lt;strong&gt;&amp;ldquo;A Multi-Method Validation Framework for Large-Scale Multilingual Text Analytics&amp;rdquo;&lt;/strong&gt;, developed with Professor &lt;strong&gt;D. Fioredistella Iezzi&lt;/strong&gt; (Director of the Data Science Master at the University of Rome Tor Vergata).&lt;/p&gt;
&lt;h3 id="research-summary"&gt;Research Summary&lt;/h3&gt;
&lt;p&gt;The study presents a validation framework tested on over 999,000 multilingual reviews to evaluate model consistency across methodologies. The empirical results show that over 95% of output variance is driven by text content, whereas less than 3% is attributable to algorithmic variation, demonstrating that robust analytical conclusions remain consistent across computational approaches.&lt;/p&gt;
&lt;p&gt;The research evaluated corpus data made available by Professor &lt;strong&gt;Massimo Regoli&lt;/strong&gt;, to whose memory the paper is dedicated.&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;
&lt;/li&gt;
&lt;li&gt;
&lt;/li&gt;
&lt;/ul&gt;</description></item></channel></rss>